generating-infrastructure-as-code

Warn

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/iac_generate.py script generates shell scripts and marks them as executable using chmod(0o755). This dynamic script generation is a risk if the input source is untrusted, as it could lead to arbitrary command execution.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided descriptions to generate code. Ingestion points: Natural language requests in SKILL.md. Boundary markers: Absent. Capability inventory: Bash access to aws, gcloud, az, and terraform commands. Sanitization: Absent in the provided scripts.
  • [COMMAND_EXECUTION]: The skill requests broad execution permissions for cloud CLIs and Terraform via Bash tool configurations in SKILL.md. This level of access increases the potential impact of malicious input or code generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 12:02 PM